Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/marcuskrogh-model
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/model
What's inside
- Skill name
model- Description
- Mathematical alignment through LaTeX-only questions. Produces MODEL.md finding docs on the delivery branch (no separate PR). Use for dynamical models, OCP, estimators, or applied math.
- License
- MIT
- Instructions
- 85 lines in SKILL.md · view on GitHub
Files (3)
- SKILL.md
- format.md
- reference.md
SKILL.md (first lines)
# Model Applies [CONCEPT_ALIGNMENT](../concepts/CONCEPT_ALIGNMENT.md) and [CONCEPT_SKILL](../concepts/CONCEPT_SKILL.md) to **applied mathematics**. Produces **finding docs** on the delivery branch. **On invoke:** read [CONCEPT_ALIGNMENT](../concepts/CONCEPT_ALIGNMENT.md), [CONCEPT_SKILL](../concepts/CONCEPT_SKILL.md), [format.md](format.md), [reference.md](reference.md), and [../workflow/SKILL.md](../workflow/SKILL.md). When a claim needs sources and `RESEARCH.md` is absent, also read [CONCEPT_RESEARCH](../concepts/CONCEPT_RESEARCH.md). Settles formulation, assumptions, and numerical choices **with the user** — not product scope, UX, behaviour, or acceptance (`/define`). `RESEARCH.md` orients questions; it does not choose the model for the user. ## Extensions | Slot | This skill | |------|------------| | **Subject** | Mathematical object (model, OCP, estimator, …) | | **Probes** | Model class; state/input/output; constraints/objectives; numerical schemes / estimation / discretisation; Task key; `RESEARCH.md` as literature only; `MODEL.md` path | | **Stop condition** | Mathematical foundations unambiguous **with the user** | | **Alignment artifact** | `MODEL.md` (path from WORKSPACE) | | **Readiness prompt** | LaTeX block: "Ready to finalise the model specification?" ([format.md](format.md)) | | **Format override** | LaTeX-only questions per [format.md](format.md) | | **Opening** | Thin: one LaTeX block — what mathematical object/problem class? Rich / Task key: load Task + RESEARCH/ROADMAP; first unresolved **math** divergence | | **Scope guard** | No code unless mathematically essential; no product/UX definition | ## Steps 1. **Resolve context** — Load the Task, Story, ROADMAP, and RESEARCH when present, then identify the first unresolved mathematical divergence. Done when the subject and supportive inputs are known. 2. **Align** — Follow the CONCEPT_ALIGNMENT flow using the extensions and LaTeX format above. Done when the mathematical stop condition holds and the user approves `MODEL.md`. 3. **Persist** — Write `MODEL.md` onto the delivery branch (no PR); when linked, apply the model tracker row. Record outcome `ready`. Apply the workflow transition. Done when the artifact is on the delivery head with Task and mirrors agreed. ## Artifact Use the definition hierarchy from [format.md](format.md): ```markdown # Model: [title] ## Problem statement / Notation / Formulation … ## Assumptions / Algorithmic choices / Numerical considerations … ## Open items … ## Role Math alignment input — not product scope or UX. ## Tracker - Task: <KEY> - Research: RESEARCH.md (if any) — supportive literature only - Branch: <delivery-branch> - PR: — (model never opens a PR) ``` ## Tracker (after approval) Follow [finding-docs continuity](../workflow/delivery.md#rules) and the [model tracker row](../workflow/tracker-sync.md#matrix). Commit `MODEL.md` onto the **delivery** Task’s branch (create the branch if needed; reuse the downstream delivery head when this is a supportive-only route Task). **Never open a PR.** Leave delivery-Task status **To Do** unless further along; mark a supportive-only route Task **Done** at handoff. Record `MODEL.md` and branch; update ROADMAP / PLAN Inputs / RESEARCH Tracker and the enabled mirror. External artifacts are pushed into the Task. ## Inputs | Input | When present | When absent | |-------|----------------|-------------| | Mathematical object to settle | Apply it | Ask, in LaTeX, what object or problem class | | `RESEARCH.md` | Apply as literature only. It does not choose the model | When a claim needs sources, apply CONCEPT_RESEARCH in this invocation, write `RESEARCH.md`, then continue | ## Output `MODEL.md` — formulation, assumptions, and numerical choices agreed with the user. Outcome: `ready`. This skill does not name a successor. Apply the workflow transition before the turn ends.
From marcuskrogh/skills, MIT.
More from marcuskrogh/skills
- 0.587score
iterate
marcuskrogh
Iteration on already merged work.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
adopt
marcuskrogh
Adopt the structure catalog across an existing codebase that was not built to it.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
define
marcuskrogh
Definition front door for concrete work.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
explore
marcuskrogh
Exploration through foggy or oversized work.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
help
marcuskrogh
Help choosing skills and workflows.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
restructure
marcuskrogh
Restructure: refactoring pass against the structure catalog (campground, names, size, cohesion, seams, named smells, CRAP).
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
architect
marcuskrogh
Architecture for one Task: record where the work sits (modules, layers, seams, dependency direction) in ARCHITECTURE.md.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
review
marcuskrogh
Review of a change as sequential or bundled lasers across Spec, Correctness, Integration, Architecture, and Standards: find, fix, then publish a code review.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
refine
marcuskrogh
Refine alignment and lightweight definition for a limited area that needs refactoring or descriptive improvement without changing behaviour.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
rework
marcuskrogh
Rework alignment and lightweight definition for an intentional implementation change that must not degrade measured outcomes.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
bug
marcuskrogh
Bug alignment and lightweight definition for a clear defect.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
implement
marcuskrogh
Implementation through managed, value-routed work packages.
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Sep 27, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/marcuskrogh/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from marcuskrogh
- 0.587score
help
marcuskrogh
Help choosing skills and workflows.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
iterate
marcuskrogh
Iteration on already merged work.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
adopt
marcuskrogh
Adopt the structure catalog across an existing codebase that was not built to it.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
define
marcuskrogh
Definition front door for concrete work.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
explore
marcuskrogh
Exploration through foggy or oversized work.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
rework
marcuskrogh
Rework alignment and lightweight definition for an intentional implementation change that must not degrade measured outcomes.
SkillAFreshness: A★ 1Claude Code +9
Cite this page
model skill. Agent Mart. https://agentmart.dev/skills/marcuskrogh-model (last updated 2026-10-24)